Transformer Architecture

14 posts · 11 sources

+3

AI EngineerYouTube3d

How MiniMax M3 Was Built: Sparse Attention and Native Multimodality — Olive Song

Hugging FaceBlog2w

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Hugging FaceBlog4w

Falcon Perception

GleanBlog10 Aug

How KV caches impact time to first token for LLMs

BasetenBlog30 Jul

22,580: GPT-2 to Kimi K3, explained

MetaBlog15 Jul

Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization

Mistral AIBlog23 Mar

Speaking of Voxtral

DeepMindBlog22 Jan

D4RT: Unified, Fast 4D Scene Reconstruction & Tracking

Hugging FaceBlog20 Jan

Differential Transformer V2

GrabBlog26 Sept

User foundation models for Grab

CerebrasBlog11 Mar

Context is Everything: Why Maximum Sequence Length Matters

CerebrasBlog3 Mar

Jais: a New Pinnacle in Open Arabic NLP

GoogleBlog29 Aug

Gemma explained: RecurrentGemma architecture- Google Developers Blog

AnthropicBlog16 Mar

Privileged Bases in the Transformer Residual Stream